Real silicon.
Published datasheet.
Every customer gets the same SKU. No "performance tier" upsell, no mystery instance type names. If you can read a datasheet, you already know what you're getting.
Real silicon.
Not a slide.
Every node is a published datasheet. Same chips, same disks, same network — for everyone.
What's actually in the box.
Compute
Modern server-class x86 — both AMD and Intel SKUs in the fleet so you can match your workload's price/performance curve. Dozens of SKUs across compute-, memory-, and storage-optimized profiles, all billed per second.
Memory
ECC across the fleet. Same memory profile in every host, every region — no surprise downclocking based on which node you happened to land on.
Storage
All-flash NVMe, network-attached so a host failure doesn't take your data with it. Replicated across drives at the storage tier — drive loss is survivable without intervention. Snapshots are first-class: schedule them with cron expressions and a retention count, restore in a single API call.
Network
50 Gbps per host on a 100 GbE backbone. Native IPv6 /64 per project, IPv4 included. Per-VM and per-network bandwidth caps when you need them. Traffic between your resources in the same region is free; egress to the internet bills against your plan's transfer allowance, and we don't charge once you're past it without saying so.
Get on the metal,
at half price.
We're shipping closed beta now. Drop your email — first hundred founders get half off everything for the first three months. No credit card. No "schedule a call."